Faster semantic search for judicial, exam, and patent corpora

Highlights

• ★Outbound query embeddings now go through a dedicated managed endpoint — p99 latency near-zero on timeouts
• ★Bulk preprocessing (chunk embed, backfill) split from outbound query traffic — no more outbound degradation during corpus backfill
• ★Zero user-facing changes: tool signatures, response schema, and env vars are all unchanged
• ★OpenData container v1.22 already shipped and running behind Twinkle Hub — everyone is on the new path

Example prompts

• Find 2024 Kaohsiung District Court trademark-infringement rulings (noticeably faster)
• Bar exam questions on "director liability"
• TSMC EUV-related patents after 2023

Dataset IDs

judicial-judgmentsmoex-examtipo-patents